Spatial-Temporal Multi-level Association for Video Object Segmentation

arXiv:2404.06265v1 Announce Type: new
Abstract: Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel processing simultaneously, thereby constraining the learning of dynamic, target-aware features. To tackle these limitations, this paper proposes a spatial-temporal multi-level association framework, which jointly associates reference frame, test frame, and object features to achieve sufficient interaction and parallel target ID association with a spatial-temporal memory …

abstract arxiv association cs.cv dynamic eess.iv feature features focus however limitations modeling object paper processing segmentation semi-supervised spatial temporal type video